paper-with-me

Papers

Exploring Diffusion and Flow Matching Under Generator Matching

2024-12-15 · Zeeshan Patel, James DeLoye, Lance Mathias

In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.

📄 PDF Abstract BibTeX arXiv:2412.11024

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Time dependent loss reweighting for flow matching and diffusion models is theoretically justified

2025-11-20 · Lukas Billera, Hedwig Nora Nordlinder, Ben Murrell arxiv

This brief note clarifies that, in Generator Matching (which subsumes a large family of flow matching and diffusion models over continuous, manifold, and discrete spaces), both the Bregman divergence loss and the linear …

Generator Matching: Generative modeling with arbitrary Markov processes

2024-10-27 · Peter Holderrieth, Marton Havasi, Jason Yim, Neta Shaul 외

We introduce generator matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for gene…

Image Generation

Score Distillation of Flow Matching Models

2025-09-29 · Mingyuan Zhou, Yi Gu, Huangjie Zheng, Liangchen Song 외 arxiv

Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a di…

Image Generation

Emyx: Fast and efficient all-atom protein generation

2026-06-12 · Nicholas J. Williams, Ward Haddadin, Matteo P. Ferla, Constantin Schneider 외 arxiv

Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the underlying generative model. Current al…

Energy-based generator matching: A neural sampler for general state space

2025-05-26 · Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong 외

We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables trai…